Is the Rocket Fuel skill free?

Yes. The skill itself is free from NulightJens/rocket-fuel-skill. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Rocket Fuel SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Rocket Fuel?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Rocket Fuel with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Rocket Fuel

Claude plans, Codex CLI attacks the plan and builds it, Claude runs the proof

by NulightJens · NulightJens/rocket-fuel-skill

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Aug 5, 2026
Environment: Claude Code 2.x (agent harness)

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Aug 5, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran the standalone Same Page Meeting for real: the bundled codex exec contract launched Codex CLI 0.146.0 read-only against a five-rock plan and came back with 18 findings in 69 seconds, against the 6 the same plan drew from a solo no-skill review. Round 2 resumed the same thread id and caught something the solo pass missed completely, that a '100k samples, zero duplicates' test on 6-char base62 codes flakes on the birthday paradox about 8% of the time (measured: 8.43%). The read-only sandbox held on both rounds, with git status clean after each call, and the VERDICT line parsed exactly as the contract documents. The entry cost is real: Codex CLI 0.130+ plus a logged-in OpenAI or ChatGPT account, and the full build-and-proof pipeline was not run end to end.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Rocket Fuel does

Runs Claude as the Visionary and the OpenAI Codex CLI as the Integrator on one project: Claude writes the VTO and rock plan, Codex reviews it read-only in a bounded adversarial loop until a VERDICT line lands, then builds each rock in its own sandbox while Claude reviews the diff and runs the proof command. Triggers on /rocket-fuel, on starting or refactoring a project with Codex, on asking for a plan to be pressure-tested by a second model, and on delegating a scoped build. Requires the Codex CLI 0.130+ and a logged-in OpenAI account.

How to install Rocket Fuel

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Rocket Fuel

/rocket-fuel Claude plans, Codex CLI attacks the plan and builds it, Claude runs the proof

It also activates on plain-language prompts like these:

Have Codex pressure-test my PLAN.md before I start building
/rocket-fuel build me a habit tracker CLI from scratch
Get a second model to review this rock plan for gaps

Frequently asked questions

Is the Rocket Fuel skill free?: Yes. The skill itself is free from NulightJens/rocket-fuel-skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Rocket Fuel work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Aug 5, 2026. Verdict: Tested · Works. Ran the standalone Same Page Meeting for real: the bundled codex exec contract launched Codex CLI 0.146.0 read-only against a five-rock plan and came back with 18 findings in 69 seconds, against the 6 the same plan drew from a solo no-skill review. Round 2 resumed the same thread id and caught something the solo pass missed completely, that a '100k samples, zero duplicates' test on 6-char base62 codes flakes on the birthday paradox about 8% of the time (measured: 8.43%). The read-only sandbox held on both rounds, with git status clean after each call, and the VERDICT line parsed exactly as the contract documents. The entry cost is real: Codex CLI 0.130+ plus a logged-in OpenAI or ChatGPT account, and the full build-and-proof pipeline was not run end to end.
What is the Rocket Fuel SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Rocket Fuel?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Rocket Fuel with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.